© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129507
    Prev
    Next
    INDEX
    Explanations

    questions, captions, and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    SQL or database connection code in programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vají
    -1.23
    nisk
    -1.18
     Kegiatan
    -1.15
    :
    -1.14
     Makanan
    -1.12
     how
    -1.09
    🏗
    -1.05
    Վ
    -1.04
    就好了
    -1.02
     Penelitian
    -1.02
    POSITIVE LOGITS
    Kde
    1.22
    träd
    1.22
     of
    1.21
    MfG
    1.19
    Fonto
    1.19
    Espace
    1.18
     CGPA
    1.17
     зоны
    1.16
    THANK
    1.12
    #--
    1.10
    Activations Density 0.002%

    No Known Activations